A British mathematician is applying "big data" algorithms to detect Parkinson's disease from voice recordings and now claims accuracy up to 99 percent.

"We also know how to predict the severity of symptoms to within a few percentage points of clinical judgment," Max Little, a mathematician on the faculty of Aston University in Birmingham, England, and a visiting researcher at both the Massachusetts Institute of Technology and Oxford University, wrote Friday in the Huffington Post's TED Weekends column. He gave a TED talk in Edinburgh, Scotland, last June.

The technology has the potential to make drastic cuts to the time and cost of diagnosing Parkinson's, a neurological disease that manifests itself not only through the telltale physical tremors but through changes in speech patterns, among half a dozen other typical symptoms.

"Current symptom tests are done in a clinic. They are expensive, time-consuming, and logistically difficult. So mostly, these tests are not done outside clinical trials," Little wrote. "Our technology could enable some radical breakthroughs, because voice-based tests can be administered remotely, and patients can do the tests themselves. Also, they are high speed, taking less than 30 seconds, and since they don't involve expert staff time, they are ultra low cost. That makes the technology massively scalable."

Little founded the Parkinson's Voice Initiative and is in the process of analyzing 10,000 phone calls he and his team collected for a current research project. He has been working on the project for seven years since a friend, spurred on by the fact that a friend, a former ballet dancer, suffers from Parkinson's disease.

"This incredible and unique dataset will tell us whether it is possible to use something as ubiquitous as the telephone to detect and monitor the disease," Little said. "This now becomes a 'big data' analysis problem, and until the analysis is done, we can't know for sure if it will work. But if it does, we would have the technology to check out some 75 percent of the world's population at a negligible cost."

Little reported achieving 86 percent accuracy with mathematical algorithms he developed while working a Ph.D. at Oxford. As a professional, he said he now has algorithms that come close to 99 percent in laboratory conditions.

If the analysis does prove successful on a wide scale, Little said the technology could eliminate some physician office visits by providing a remote means of monitoring how Parkinson's is progressing and also assist in research projects. "We could do high-frequency monitoring for individualized treatment decisions. This might allow clinicians to optimize drug timing and dosage," Little surmised.

"For clinical trials, we could do cost-effective mass recruitment for new treatments. By recruiting very large numbers into trials we could help speed up the search for a cure. And finally, this could enable population-scale screening programs, that might allow us to search for 'biomarkers' that show early signs of the disease before the damage done is irreparable," he continued.

Little also said scientists in other fields might be able to apply his algorithms outside medicine. "One particularly fascinating application is the detection of extrasolar planets — that is, planets circling other stars," he wrote.

While the voice angle is new, this is not the first time someone has tried to bring mobile technology to Parkison's care. Great Lakes Neurotechnologies has won FDA 510(k) clearance for Kinesia HomeView, which combines a tablet computer and wireless sensors to assess the effectiveness of treatments for Parkinsonian tremors.